About this document

Learning Humanoid Getting-Up Policies by fireworkszhang is a document available to read on EtoBox.

This paper presents H UMAN UP, a two-stage reinforcement learning framework designed to enable humanoid robots to recover from falls by getting up from various postures on different terrains. The framework addresses the challenges of non-periodic behavior, rich contact patterns, and reward sparsity through a curriculum that progresses from simpler to more complex scenarios. Experimental results demonstrate the effectiveness of the learned policies in real-world applications, significantly enhancing the capa

Author

fireworkszhang

Language

EN